Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    205
    -0.07
    _FAST
    -0.07
     governance
    -0.07
    RULE
    -0.06
     với
    -0.06
     transcripts
    -0.06
    -js
    -0.06
    _ca
    -0.06
    Hibernate
    -0.06
     Humanities
    -0.06
    POSITIVE LOGITS
    ivet
    0.06
     adec
    0.06
     revered
    0.06
    .getError
    0.06
    [table
    0.06
    ENDING
    0.06
     октября
    0.06
    rement
    0.06
    lič
    0.06
    /{$
    0.06
    Act Density 0.057%

    No Known Activations